AI Backend Engineer

AI Backend Engineer

Payments & Reconciliation

Department: Engineering

Reports to: CTO

About the Company

They’re crafting the finance-first All-In-One Operating System for Education in Latin America—unifying payments, billing, collections, student systems, academic flows, communication, and financial ops.
Serving 1,000+ schools in Mexico, Colombia, and Ecuador, they empower hundreds of thousands of families with modern, rock-solid experiences for parents, students, teachers, and admins.
Backed by elite global fintech and edtech investors.
Their mission: equip schools to run with precision, accuracy, and unshakeable confidence—fueled by cutting-edge tech and AI automation.
As they scale across LATAM, AI stands as the unbreakable core of their product and engineering dominance.

Role Overview

They’re hunting an AI Engineer to architect, construct, and unleash AI-native systems that ignite automation, intelligence, and operational supremacy across their products: Payments, Collections, SIS, Billing, Factoring, and Credit.
You’ll dominate the crossroads of LLM engineering, backend mastery, data orchestration, and agentic firepower, morphing chaotic manual ops into hyper-scalable AI juggernauts for thousands of schools and hordes of families.
This gig fuses backend sorcery, LLM symphonies, RAG arteries, evaluators, agents, and GenAI fortresses. You’ll lock arms with Product, Data, Backend, and Ops to alchemize vague business riddles into battle-hardened AI weapons that shift massive financial tides.
High-stakes, total-ownership in a blistering arena—for builders of genuine, production-grade AI, not toy prototypes.

What You’ll Lead

1. Build & Deploy AI Systems

• Design and build AI-powered microservices (Python/FastAPI) for inference and decision automation

• Implement LLM workflows using LangChain, LangGraph, CrewAI, AutoGen, or MCP-based architectures

• Build RAG pipelines: ingestion, chunking, embeddings, retrieval, re-ranking

• Integrate AI features into the company’s products (Payments, Collections, Billing, SIS)

2. AI Agents & Automation

• Build agentic workflows for data reconciliation, anomaly detection, financial validation, compliance checks, and school-specific automations

• Design structured tool-calling, guardrails, and self-correction loops

• Implement event-driven AI pipelines connected to Kafka/SQS

3. Retrieval, Data & Evaluation

• Implement and optimize vector stores (pgvector, FAISS, Weaviate, Milvus)

• Create evaluation dashboards and automated evals to benchmark AI reliability

• Build observability around prompts, costs, latencies, and error handling

4. Backend, APIs & Systems Engineering

• Build scalable APIs integrating AI models with the company’s microservice ecosystem

• Deploy AI services on AWS using ECS, Lambda, SQS, Aurora, Redis, S3

• Ensure security, compliance, PII protection, and safe AI usage

5. Product & Cross-Functional Collaboration

• Partner with Product and Operations to translate business needs into AI features

• Convert prototypes into robust, production-ready services

• Work with Data Engineering to power training, feature engineering, and retrieval

Required Qualifications

• 4+ years in software engineering, data engineering, or ML engineering

• 1+ year hands-on forging LLM-powered systems (agents, RAG, pipelines, evaluators)

• Steel-sharp Python skills; FastAPI edge preferred

• Battle-tested with LangChain, LangGraph, CrewAI, AutoGen, or MCP

• Vector DB mastery: FAISS, Milvus, pgvector, Pinecone

• Seamless integration of OpenAI, Anthropic, Mistral, Gemini, Groq, or kin APIs

• SQL fluency and relational dominance (PostgreSQL/Aurora)

• Command of REST/gRPC API architecture

• Relentless ownership and action bias

• Skill to weaponize ambiguous problems into rapid-fire solutions

• Crystal-clear communication and collab prowess

• Thrives in startup velocity

• Full pro fluency in Spanish and English (written & spoken)

Preferred Qualifications

• Experience with:

  • RAG optimization (hybrid search, re-ranking)

  • AI observability (OpenTelemetry, Evidently, custom evals)

  • Redis, Kafka, SQS, event-driven architectures

  • Prompt engineering & safety pipelines

• Prior firepower in fintech, payments, or mission-critical systems

Responsibilities may vary, but can include

• Build and own AI microservices end-to-end

• Design and implement agentic workflows for automation across billing, reconciliation, collections, SIS

• Evaluate and tune LLM performance, latency, cost, reliability

• Implement guardrails, safety policies, and PII protection

• Collaborate in code reviews, architecture discussions, and roadmap planning

• Document workflows, APIs, prompts, evals, and data flows

Why Join

• Become a cornerstone of the new AI Engineering powerhouse

• Forge AI systems delivering tangible financial and operational blasts

• Team up with elite engineering, product, and AI squads

• Shape reliability for millions of tuition transactions annually

• Remote-first vibe with autonomy, ownership, and rocket-fuel growth

• Chance to architect LATAM’s ed-fintech backbone

• Career acceleration as product, engineering, and platform explode

Location: Flexible (remote from Latin America)
Travel: Occasional to Mexico City for team onsites

If you're ready to unleash AI on LATAM's ed-fintech frontier, fire over your CV and standout projects. Let's ignite ⚡